|
|
--- |
|
|
tags: |
|
|
- sentence-transformers |
|
|
- cross-encoder |
|
|
- generated_from_trainer |
|
|
- dataset_size:610 |
|
|
- loss:FitMixinLoss |
|
|
base_model: cross-encoder/mmarco-mMiniLMv2-L12-H384-v1 |
|
|
pipeline_tag: text-ranking |
|
|
library_name: sentence-transformers |
|
|
--- |
|
|
|
|
|
# CrossEncoder based on cross-encoder/mmarco-mMiniLMv2-L12-H384-v1 |
|
|
|
|
|
This is a [Cross Encoder](https://www.sbert.net/docs/cross_encoder/usage/usage.html) model finetuned from [cross-encoder/mmarco-mMiniLMv2-L12-H384-v1](https://huggingface.co/cross-encoder/mmarco-mMiniLMv2-L12-H384-v1) using the [sentence-transformers](https://www.SBERT.net) library. It computes scores for pairs of texts, which can be used for text reranking and semantic search. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
- **Model Type:** Cross Encoder |
|
|
- **Base model:** [cross-encoder/mmarco-mMiniLMv2-L12-H384-v1](https://huggingface.co/cross-encoder/mmarco-mMiniLMv2-L12-H384-v1) <!-- at revision 1427fd652930e4ba29e8149678df786c240d8825 --> |
|
|
- **Maximum Sequence Length:** 512 tokens |
|
|
- **Number of Output Labels:** 1 label |
|
|
<!-- - **Training Dataset:** Unknown --> |
|
|
<!-- - **Language:** Unknown --> |
|
|
<!-- - **License:** Unknown --> |
|
|
|
|
|
### Model Sources |
|
|
|
|
|
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net) |
|
|
- **Documentation:** [Cross Encoder Documentation](https://www.sbert.net/docs/cross_encoder/usage/usage.html) |
|
|
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) |
|
|
- **Hugging Face:** [Cross Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=cross-encoder) |
|
|
|
|
|
## Usage |
|
|
|
|
|
### Direct Usage (Sentence Transformers) |
|
|
|
|
|
First install the Sentence Transformers library: |
|
|
|
|
|
```bash |
|
|
pip install -U sentence-transformers |
|
|
``` |
|
|
|
|
|
Then you can load this model and run inference. |
|
|
```python |
|
|
from sentence_transformers import CrossEncoder |
|
|
|
|
|
# Download from the 🤗 Hub |
|
|
model = CrossEncoder("cross_encoder_model_id") |
|
|
# Get scores for pairs of texts |
|
|
pairs = [ |
|
|
['Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.', 'Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.'], |
|
|
['3. Die Fondsleitung darf einschliesslich der Derivate und strukturierten Produkte höchstens 10% des Vermögens eines Teilvermogens in Effekten und Geldmarktinstrumenten desselben Emittenten anlegen.', '3. Die Fondsleitung darf einschliesslich der Derivate und strukturierten Produkte höchstens 10% des Vermögens eines Teilvermogens in Effekten und Geldmarktinstrumenten desselben Emittenten anlegen.'], |
|
|
['Das Teilvermögen BLKB iQ Fund (CH) iQ Responsible Vorsorge Balanced darf bis zu 100% der Anteile des BLKB iQ Fund (CH) iQ Responsible Bond Fund CHF erwerben.', 'Maximalanteil pro Emission: Höchstens 30 Prozent des Fondsvermögens dürfen in Effekten und Geldmarktinstrumenten derselben Emission angelegt werden.'], |
|
|
['e) Geldmarktinstrumente, wenn diese liquide und bewertbar sind sowie an einer Börse oder an einem anderen geregelten, dem Publikum offenstehenden Markt gehandelt werden; Geldmarktinstrumente, die nicht an einer Börse oder an einem anderen geregelten, dem Publikum offenstehenden Markt gehandelt werden, dürfen nur erworben werden, wenn die Emission oder der Emittent Vorschriften über den Gläubigerund den Anlegerschutz unterliegt und wenn die Geldmarktinstrumente von Emittenten gemäss Artikel 74 Absatz 2 KKV begeben oder garantiert sind.', 'Institution: beaufsichtigte Bank oder Institut: Geldmarktinstrumente müssen von einer Bank, einem Effektenhändler oder einem anderen beaufsichtigten Institut begeben oder garantiert sein, das einer Aufsicht untersteht, die der Schweizer Aufsicht gleichwertig ist.'], |
|
|
['d) Termingeschäfte (Futures und Forwards), deren Wert linear vom Wert des Basiswertes abhängt.', 'Derivate: Derivative Finanzinstrumente sind zulässig, wenn ihnen als Basiswerte Anlagen im Sinne von Artikel 70 Absatz 1 Buchstaben a-d, Finanzindizes, Zinssätze, Wechselkurse, Kredite oder Währungen zugrunde liegen.'], |
|
|
] |
|
|
scores = model.predict(pairs) |
|
|
print(scores.shape) |
|
|
# (5,) |
|
|
|
|
|
# Or rank different texts based on similarity to a single text |
|
|
ranks = model.rank( |
|
|
'Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.', |
|
|
[ |
|
|
'Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.', |
|
|
'3. Die Fondsleitung darf einschliesslich der Derivate und strukturierten Produkte höchstens 10% des Vermögens eines Teilvermogens in Effekten und Geldmarktinstrumenten desselben Emittenten anlegen.', |
|
|
'Maximalanteil pro Emission: Höchstens 30 Prozent des Fondsvermögens dürfen in Effekten und Geldmarktinstrumenten derselben Emission angelegt werden.', |
|
|
'Institution: beaufsichtigte Bank oder Institut: Geldmarktinstrumente müssen von einer Bank, einem Effektenhändler oder einem anderen beaufsichtigten Institut begeben oder garantiert sein, das einer Aufsicht untersteht, die der Schweizer Aufsicht gleichwertig ist.', |
|
|
'Derivate: Derivative Finanzinstrumente sind zulässig, wenn ihnen als Basiswerte Anlagen im Sinne von Artikel 70 Absatz 1 Buchstaben a-d, Finanzindizes, Zinssätze, Wechselkurse, Kredite oder Währungen zugrunde liegen.', |
|
|
] |
|
|
) |
|
|
# [{'corpus_id': ..., 'score': ...}, {'corpus_id': ..., 'score': ...}, ...] |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### Direct Usage (Transformers) |
|
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Downstream Usage (Sentence Transformers) |
|
|
|
|
|
You can finetune this model on your own dataset. |
|
|
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Out-of-Scope Use |
|
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Bias, Risks and Limitations |
|
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Recommendations |
|
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
|
--> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Dataset |
|
|
|
|
|
#### Unnamed Dataset |
|
|
|
|
|
* Size: 610 training samples |
|
|
* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code> |
|
|
* Approximate statistics based on the first 610 samples: |
|
|
| | sentence_0 | sentence_1 | label | |
|
|
|:--------|:--------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------|:--------------------------------------------------------------| |
|
|
| type | string | string | float | |
|
|
| details | <ul><li>min: 30 characters</li><li>mean: 233.99 characters</li><li>max: 1055 characters</li></ul> | <ul><li>min: 30 characters</li><li>mean: 202.09 characters</li><li>max: 696 characters</li></ul> | <ul><li>min: 0.0</li><li>mean: 0.5</li><li>max: 1.0</li></ul> | |
|
|
* Samples: |
|
|
| sentence_0 | sentence_1 | label | |
|
|
|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| |
|
|
| <code>Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.</code> | <code>Die Einzellimiten von Ziffer 3 und 5 jedoch dürfen mit der vorliegenden Limite von 35% nicht kumuliert werden.</code> | <code>1.0</code> | |
|
|
| <code>3. Die Fondsleitung darf einschliesslich der Derivate und strukturierten Produkte höchstens 10% des Vermögens eines Teilvermogens in Effekten und Geldmarktinstrumenten desselben Emittenten anlegen.</code> | <code>3. Die Fondsleitung darf einschliesslich der Derivate und strukturierten Produkte höchstens 10% des Vermögens eines Teilvermogens in Effekten und Geldmarktinstrumenten desselben Emittenten anlegen.</code> | <code>1.0</code> | |
|
|
| <code>Das Teilvermögen BLKB iQ Fund (CH) iQ Responsible Vorsorge Balanced darf bis zu 100% der Anteile des BLKB iQ Fund (CH) iQ Responsible Bond Fund CHF erwerben.</code> | <code>Maximalanteil pro Emission: Höchstens 30 Prozent des Fondsvermögens dürfen in Effekten und Geldmarktinstrumenten derselben Emission angelegt werden.</code> | <code>0.0</code> | |
|
|
* Loss: [<code>FitMixinLoss</code>](https://sbert.net/docs/package_reference/cross_encoder/losses.html#fitmixinloss) |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `per_device_train_batch_size`: 1 |
|
|
- `per_device_eval_batch_size`: 1 |
|
|
- `num_train_epochs`: 20 |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: no |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 1 |
|
|
- `per_device_eval_batch_size`: 1 |
|
|
- `per_gpu_train_batch_size`: None |
|
|
- `per_gpu_eval_batch_size`: None |
|
|
- `gradient_accumulation_steps`: 1 |
|
|
- `eval_accumulation_steps`: None |
|
|
- `torch_empty_cache_steps`: None |
|
|
- `learning_rate`: 5e-05 |
|
|
- `weight_decay`: 0.0 |
|
|
- `adam_beta1`: 0.9 |
|
|
- `adam_beta2`: 0.999 |
|
|
- `adam_epsilon`: 1e-08 |
|
|
- `max_grad_norm`: 1 |
|
|
- `num_train_epochs`: 20 |
|
|
- `max_steps`: -1 |
|
|
- `lr_scheduler_type`: linear |
|
|
- `lr_scheduler_kwargs`: {} |
|
|
- `warmup_ratio`: 0.0 |
|
|
- `warmup_steps`: 0 |
|
|
- `log_level`: passive |
|
|
- `log_level_replica`: warning |
|
|
- `log_on_each_node`: True |
|
|
- `logging_nan_inf_filter`: True |
|
|
- `save_safetensors`: True |
|
|
- `save_on_each_node`: False |
|
|
- `save_only_model`: False |
|
|
- `restore_callback_states_from_checkpoint`: False |
|
|
- `no_cuda`: False |
|
|
- `use_cpu`: False |
|
|
- `use_mps_device`: False |
|
|
- `seed`: 42 |
|
|
- `data_seed`: None |
|
|
- `jit_mode_eval`: False |
|
|
- `use_ipex`: False |
|
|
- `bf16`: False |
|
|
- `fp16`: False |
|
|
- `fp16_opt_level`: O1 |
|
|
- `half_precision_backend`: auto |
|
|
- `bf16_full_eval`: False |
|
|
- `fp16_full_eval`: False |
|
|
- `tf32`: None |
|
|
- `local_rank`: 0 |
|
|
- `ddp_backend`: None |
|
|
- `tpu_num_cores`: None |
|
|
- `tpu_metrics_debug`: False |
|
|
- `debug`: [] |
|
|
- `dataloader_drop_last`: False |
|
|
- `dataloader_num_workers`: 0 |
|
|
- `dataloader_prefetch_factor`: None |
|
|
- `past_index`: -1 |
|
|
- `disable_tqdm`: False |
|
|
- `remove_unused_columns`: True |
|
|
- `label_names`: None |
|
|
- `load_best_model_at_end`: False |
|
|
- `ignore_data_skip`: False |
|
|
- `fsdp`: [] |
|
|
- `fsdp_min_num_params`: 0 |
|
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
|
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
|
- `deepspeed`: None |
|
|
- `label_smoothing_factor`: 0.0 |
|
|
- `optim`: adamw_torch |
|
|
- `optim_args`: None |
|
|
- `adafactor`: False |
|
|
- `group_by_length`: False |
|
|
- `length_column_name`: length |
|
|
- `ddp_find_unused_parameters`: None |
|
|
- `ddp_bucket_cap_mb`: None |
|
|
- `ddp_broadcast_buffers`: False |
|
|
- `dataloader_pin_memory`: True |
|
|
- `dataloader_persistent_workers`: False |
|
|
- `skip_memory_metrics`: True |
|
|
- `use_legacy_prediction_loop`: False |
|
|
- `push_to_hub`: False |
|
|
- `resume_from_checkpoint`: None |
|
|
- `hub_model_id`: None |
|
|
- `hub_strategy`: every_save |
|
|
- `hub_private_repo`: None |
|
|
- `hub_always_push`: False |
|
|
- `hub_revision`: None |
|
|
- `gradient_checkpointing`: False |
|
|
- `gradient_checkpointing_kwargs`: None |
|
|
- `include_inputs_for_metrics`: False |
|
|
- `include_for_metrics`: [] |
|
|
- `eval_do_concat_batches`: True |
|
|
- `fp16_backend`: auto |
|
|
- `push_to_hub_model_id`: None |
|
|
- `push_to_hub_organization`: None |
|
|
- `mp_parameters`: |
|
|
- `auto_find_batch_size`: False |
|
|
- `full_determinism`: False |
|
|
- `torchdynamo`: None |
|
|
- `ray_scope`: last |
|
|
- `ddp_timeout`: 1800 |
|
|
- `torch_compile`: False |
|
|
- `torch_compile_backend`: None |
|
|
- `torch_compile_mode`: None |
|
|
- `include_tokens_per_second`: False |
|
|
- `include_num_input_tokens_seen`: False |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `liger_kernel_config`: None |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: False |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `multi_dataset_batch_sampler`: proportional |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
| Epoch | Step | Training Loss | |
|
|
|:-------:|:-----:|:-------------:| |
|
|
| 0.8197 | 500 | 1.9143 | |
|
|
| 1.6393 | 1000 | 0.7914 | |
|
|
| 2.4590 | 1500 | 0.5883 | |
|
|
| 3.2787 | 2000 | 0.3915 | |
|
|
| 4.0984 | 2500 | 0.2119 | |
|
|
| 4.9180 | 3000 | 0.2049 | |
|
|
| 5.7377 | 3500 | 0.1157 | |
|
|
| 6.5574 | 4000 | 0.1367 | |
|
|
| 7.3770 | 4500 | 0.0336 | |
|
|
| 8.1967 | 5000 | 0.0912 | |
|
|
| 9.0164 | 5500 | 0.0517 | |
|
|
| 9.8361 | 6000 | 0.1057 | |
|
|
| 10.6557 | 6500 | 0.037 | |
|
|
| 11.4754 | 7000 | 0.0875 | |
|
|
| 12.2951 | 7500 | 0.057 | |
|
|
| 13.1148 | 8000 | 0.0274 | |
|
|
| 13.9344 | 8500 | 0.0277 | |
|
|
| 14.7541 | 9000 | 0.0133 | |
|
|
| 15.5738 | 9500 | 0.0473 | |
|
|
| 16.3934 | 10000 | 0.0272 | |
|
|
| 17.2131 | 10500 | 0.025 | |
|
|
| 18.0328 | 11000 | 0.0481 | |
|
|
| 18.8525 | 11500 | 0.0111 | |
|
|
| 19.6721 | 12000 | 0.0226 | |
|
|
|
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.11.13 |
|
|
- Sentence Transformers: 4.1.0 |
|
|
- Transformers: 4.53.3 |
|
|
- PyTorch: 2.6.0+cu124 |
|
|
- Accelerate: 1.9.0 |
|
|
- Datasets: 4.0.0 |
|
|
- Tokenizers: 0.21.2 |
|
|
|
|
|
## Citation |
|
|
|
|
|
### BibTeX |
|
|
|
|
|
#### Sentence Transformers |
|
|
```bibtex |
|
|
@inproceedings{reimers-2019-sentence-bert, |
|
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
|
month = "11", |
|
|
year = "2019", |
|
|
publisher = "Association for Computational Linguistics", |
|
|
url = "https://arxiv.org/abs/1908.10084", |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## Glossary |
|
|
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Authors |
|
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Contact |
|
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
|
--> |
